CN107885744B - Conversational data analysis - Google Patents

Abstract

Embodiments of the present disclosure relate to conversational data analysis. After receiving a data analysis request of a user, heuristic information may be determined based on the data analysis request. The heuristic information referred to herein is not the result of analyzing the request for the data, but rather information that may be used to direct the session to proceed. The user may provide supplemental information associated with the data analysis request based on such heuristic information, such as clarifying the meaning of the data analysis request, making a related further analysis request, and so forth. Based on the supplemental information from the user, the user can be provided with its true needs and meaningful data analysis results. In this way, the data analysis will be more accurate and efficient. The user can have good user experience while obtaining truly helpful information.

Description

Conversational Data Analysis

Background technique

Data analysis plays a very important role in many application areas such as data-driven decision-making systems. Users can submit data queries to data analysis tools to query data and create visual reports from desired perspectives. In order to make data analysis more convenient and easy to use, a scheme of applying natural language processing to a user interface for data analysis has been proposed. Natural language processing refers to the technology of using computers to process human language, which enables computers to understand human language.

Traditional data analysis solutions based on natural language processing are mainly based on a single input box approach. When receiving a data analysis request in the form of natural language input by the user, the machine performs the corresponding operation and provides the corresponding result. For simple or basic data analysis requests, this data analysis solution can usually obtain corresponding data analysis results. However, for complex data analysis requests, existing data analysis solutions are often difficult to correctly understand the real intention of the user, and thus cannot provide the data analysis results required by the user.

Contents of the invention

In order to solve the above and potential problems, embodiments of the present disclosure provide a two-way conversational data analysis method and device. According to an embodiment of the present disclosure, a user can complete a data analysis request in a dialog with a machine. After receiving the user's data analysis request, heuristic information can be determined based on the data analysis request. The heuristic information referred to here is not the result of the data analysis request, but information that can be used to guide the conversation to continue. The user may provide supplementary information associated with the data analysis request based on such enlightening information, such as clarifying the meaning of the data analysis request, making a related further analysis request, and so on. According to the supplementary information from the user, it can provide the user with the data analysis results that they really need and meaningful. In this way, data analysis will be more accurate and efficient. Users can have a good user experience while getting really helpful information.

This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or principal characteristics of the disclosure, nor is it intended to limit the scope of the disclosure.

Description of drawings

The above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, the same or similar reference numerals indicate the same or similar elements, wherein:

FIG. 1 shows a block diagram of a computing environment 100 in which one or more embodiments of the present disclosure may be implemented;

FIG. 2 shows a schematic diagram of a data set 200 for performing data analysis according to an embodiment of the present disclosure;

FIG. 3 shows a schematic diagram 300 of performing data analysis on a data set 200 according to an embodiment of the present disclosure;

FIG. 4A shows a schematic diagram 400 of performing data analysis on a data set 200 according to an embodiment of the present disclosure;

FIG. 4B shows a schematic diagram 450 of a data analysis process for a two-way dialogue based on the heuristic information in FIG. 4A according to an embodiment of the present disclosure;

FIG. 5 shows a flowchart of a method 500 for data analysis according to an embodiment of the present disclosure;

FIG. 6 shows a flowchart of a method 600 for data analysis according to an embodiment of the present disclosure;

FIG. 7 illustrates a user interface 700 for multiple dialogs according to an embodiment of the disclosure; and

FIG. 8 illustrates a user interface 800 according to an embodiment of the disclosure.

Throughout the drawings, the same or similar reference numerals denote the same or similar elements.

detailed description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein; A more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for exemplary purposes only, and are not intended to limit the protection scope of the present disclosure.

Generally, the "data analysis" described in the embodiments of the present disclosure refers to analyzing a large amount of collected data (hereinafter referred to as "data set") with appropriate statistical analysis methods, extracting useful information and forming conclusions, so as to The process of examining and summarizing data in detail.

The term "heuristic information" used in the embodiments of the present disclosure refers to information used to guide the session between the user and the data analysis device, such as information used to guide the user to clarify the data analysis request, used to provide the user with Information on the results of extended data analysis, etc. Heuristic information is different from the results generated for users' data analysis requests (hereinafter also referred to as "data analysis results").

The term "content item" used in the embodiments of the present disclosure refers to a semantic unit used to characterize data in a data set, such as words or phrases about places, times, dates, events, brands, categories, and the like.

The term "code segment" used in the embodiments of the present disclosure refers to a piece of code for implementing one or more operations associated with a content item. When this code is run with a content item as input, the resulting output can be part or all of the results of a data analysis request.

As used in this disclosure, the term "comprise" and its variations are open-ended, ie "including but not limited to". The term "based on" is "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one further embodiment". Relevant definitions of other terms will be given in the description below.

Traditionally, data analysis solutions adopt a one-way dialogue method, which can only provide corresponding data analysis results for simple or basic data analysis requests. When a user inputs a complex data analysis request, it is usually difficult for traditional data analysis solutions to understand such a complex data analysis request, thus causing the system to report errors or give wrong data analysis results. As a result, the user cannot be helped to obtain the data analysis results he/she really wants, and the user's needs cannot be met, causing the data analysis to lose its meaning.

To this end, the present disclosure proposes a two-way dialog data analysis method and device, which can not only receive a data analysis request from a user, but also generate enlightening information by analyzing the data analysis request. As used herein, the term "enlightening information" refers to information that is not the result of a data analysis and is used to guide the continuation of a data analysis conversation. For example, enlightening information can lead the user to make further explanations or supplements, resulting in questions that the device can understand. The heuristic information may also be extended information related to the user's current analysis that is actively recommended to the user by the data analysis device. Such extensibility information may be obtained, for example, from the analyzed data by the data analysis device through a data mining method. In this way, the method and device of the embodiments of the present disclosure can provide users with data analysis results that better meet their needs, and significantly improve user experience.

The basic principles and several example implementations of the present disclosure are explained below with reference to FIGS. 1 to 8 . FIG. 1 shows a block diagram of a computing environment 100 in which a data analysis device of an embodiment of the present disclosure may be implemented. It should be understood that the computing environment 100 shown in FIG. 1 is exemplary only and should not constitute any limitation on the functionality and scope of the embodiments described herein.

As shown in FIG. 1, a computing environment 100 includes a user 101 and a computing system/server 105 in the form of a general-purpose computing device. Computing system/server 105 may be used to implement the data analysis device of embodiments of the present disclosure (hereinafter also referred to as "data analysis device 105"). User 101 may interact with computing system/server 105 to make data analysis requests 102 and obtain desired data analysis results 180 . Components of computing system/server 105 may include, but are not limited to, one or more processors or processing units 110, memory 120, storage devices 130, one or more communication units 140, one or more input devices 150, and one or more output device 160. The processing unit 110 may be an actual or virtual processor and is capable of performing various processes according to programs stored in the memory 120 . In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capability of computing system/server 105 .

Computing system/server 105 typically includes multiple computer storage media. Such media can be any available media that is accessible to computing system/server 105, including but not limited to, volatile and nonvolatile media, removable and non-removable media. Memory 120 may be volatile memory (eg, registers, cache, random access memory (RAM), nonvolatile memory (eg, read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM) , flash memory) or some combination of them. Storage devices 130 may be removable or non-removable media, and may include machine-readable media, such as flash drives, magnetic disks, or any other media that may be capable of storing information and/or data 170 (e.g., data sets 172) and can be accessed within computing system/server 105 . It should be understood that the above description is only exemplary, and the data set 172 can be stored not only in the storage device 130, but also in a network storage device or any other suitable storage device.

Computing system/server 105 may further include additional removable/non-removable, volatile/nonvolatile storage media. Although not shown in FIG. 1, a disk drive for reading from or writing to a removable, nonvolatile disk and a disk drive for reading from or writing to a removable, nonvolatile disk may be provided. CD drive. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. Memory 120 may include one or more program products 122 having one or more sets of program modules configured to perform the functions of the various embodiments described herein.

The communication unit 140 enables communication with another computing device through a communication medium. Additionally, the functionality of the components of computing system/server 105 may be implemented in a single computing cluster or as a plurality of computing machines capable of communicating via communication links. Thus, computing system/server 105 may operate in a networked environment using logical connections to one or more other servers, a network personal computer (PC), or another general network node.

The input device 150 may be one or more various input devices, such as a mouse, a keyboard, a trackball, a voice input device, and the like. Output device 160 may be one or more output devices, such as a display, speakers, printer, or the like. The computing system/server 105 can also communicate with one or more external devices (not shown) through the communication unit 140 as needed, such as storage devices, display devices, etc., and one or more external devices that allow users to communicate with the computing system/server. The interacting device 105 communicates, or communicates with any device (eg, network card, modem, etc.) that enables the computing system/server 105 to communicate with one or more other computing devices. Such communication may be performed via an input/output (I/O) interface (not shown).

As shown in Figure 1, data 170 is stored in the storage device 130, which includes a data set 172 (for example, related to statistical data about sharks attacking humans in each year), and the computing system/server 105 can receive the user's 101 input through the input device 150. The data analysis request 102 of the data set 172, based on the data analysis request 102, determine the enlightening information 103 for guiding the conversation, and provide the enlightening information 103 to the user 101 through the output device 160, for guiding the user 101 to provide and analyze the data Request associated supplemental information. Then, the computing system/server 105 can complete the data analysis process based on the supplementary information, and obtain a data analysis result 180 that meets the needs of the user. Logically, the data analysis result 180 can be displayed in graphs, tables, text, audio, video or any combination thereof. It should be understood that the data analysis result 180 may be displayed in any suitable form, and the above-mentioned forms are merely exemplary and are not intended to limit the scope of the present disclosure.

Embodiments of the present disclosure are further described below through specific examples. FIG. 2 shows a schematic diagram of a data set 200 for data analysis according to an embodiment of the present disclosure. Although the data set 200 is shown in the form of a multi-dimensional table in FIG. 2, it should be understood that the data set 200 may have any suitable form, and the example in FIG. 2 is not intended to limit the scope of the present disclosure. Data set 200 may be implemented as data set 172 in data analysis device 105 of FIG. 1 .

In some embodiments, the data set 200 may be a single table stored in a database, a comma-separated value (CSV) file, or any other suitable format, or may be combined from multiple tables. As shown in FIG. 2 , in this example, dataset 200 is a table containing records of shark attacks around the world, with multiple rows and columns. Each record is a row in the table, and the columns "country" 210 , "gender" 220 , "lethality" 230 , "activity" 240 , "number of attacks" 250 and "year" 260 are data dimensions. A data model may be pre-established for the data set 200, which may include one or more content items and one or more operations associated with these content items. These content items may include data dimensions, and may also include determining other content items from these content items according to a predetermined algorithm.

Data analysis tasks for the data set 200 may include various online analysis techniques (OLAP), such as aggregation, cross analysis (Slicing and Dicing), drill-down and roll-up, and so on. Additionally, data analysis tasks may also include pattern mining, such as trends, outliers or points, correlations, and the like. Complex data analysis tasks can include multiple subtasks. By parsing the data analysis request into operations corresponding to query languages (such as SQL, DAX, and MDX) based on semantics, the data analysis task can perform such operations on the dataset 200 to obtain results for the data analysis request.

According to some embodiments of the present disclosure, the data analysis device 105 may receive various forms of data analysis requests 102 from the user 101 . This data analysis request may be a simple short sentence; it may also be a complex sentence, such as a combination of multiple simple sentences or a long sentence with many restrictions. FIG. 3 shows a schematic diagram 300 of performing data analysis on a data set 200 according to an embodiment of the present disclosure. In the embodiment of FIG. 3 , the data analysis request 102 input by the user 101 is "Please list dangerous countries by year". After receiving the data analysis request 102, the data analysis device 105 identifies one or more content items, such as "year", "danger", "country" and so on.

The data analysis device 105 then compares the identified content item with a pre-established data model for the data set 200 to determine an action associated with the identified content item. In this embodiment, the two content items "year" and "country" have associated operations defined in the data model, but the content item "danger" has not defined the corresponding operation. Therefore, the data analysis device 105 is unable to determine the action associated with the content item "dangerous". Understandably, this uncertainty is not due to the unclear meaning of the word "dangerous" per se, but rather an uncertainty about what to do with the data set based on the word.

In this case, the data analysis device 105 may generate a question for the data analysis request 102, such as "Please explain what is meant by 'dangerous' in 'dangerous country'?". This question serves to prompt the user 101 to provide clarifying information about the "dangerous" content item, thereby guiding the dialogue between the user 101 and the data analysis device 105 .

When receiving the aforementioned enlightening information 103, the user 101 may input clarifying information, for example, "the number of fatal attacks is higher than 100". This clarifying information further explains the meaning of the content item "Danger". In this way, according to the embodiment of the present disclosure, the data analysis dialog will not be terminated or an error will be reported due to uncertain operations corresponding to certain items in the analysis request. Instead, the system will steer the data analysis conversation forward by prompting the user to enter clarifying information.

Since both "fatal" and "number of attacks" belong to the content items in the established data model, the data analysis device 105 can find corresponding operations according to these content items, and implement the found operations on the data set 200 . In this embodiment, the data analysis device 105 determines that Australia and the United States are countries with more than 100 fatal attacks, that is, the "dangerous countries" input by the user 101 . In addition, the data analysis device 105 also provides a statistical chart of the number of attacks in these two countries according to the number of attacks in the year, so that the user can further view related information.

Using this two-way dialogue, the data analysis device 105 can supplement the data analysis request 102 by asking the user 101 to provide clarification information, so as to obtain a data analysis result that better meets the needs of the user. This manner reduces the possibility that the data analysis device 105 cannot obtain the data analysis result or obtains a wrong result, and significantly improves user experience.

In addition to or as a supplement to prompting the user to provide clarifying information, the data analysis device 105 may also provide the user with expanded enlightening information on the results of the data analysis. FIG. 4A shows a schematic diagram 400 of performing data analysis on a data set 200 according to an embodiment of the present disclosure. In the embodiment shown in FIG. 4A , the data analysis request 102 input by the user 101 is "check by year". After the data analysis device 105 receives the data analysis request 102, it identifies the content item "Year" from the request, and determines one or more operations associated with "Year" from the data model. By performing these operations, a curve 410 of the number of attacks counted by year can be obtained. In addition, the data analysis device 105 also applies the data analysis results to one or more predefined operation templates, thereby performing an extended analysis on the outlier 411 in the curve 410, and obtaining the following enlightening information: "Want to know about 1960 outlier problem?" and provided the corresponding options of "OK" or "No thanks".

According to an embodiment of the present disclosure, the predefined operation template may be a set including one or more operations established according to historical statistical information, profile or preference of the user 101 , access records of multiple users, and the like. In some embodiments, the predefined operational templates may be analysis of abnormal values, analysis of data trends, analysis of highest or lowest data, and the like. It should be understood that the above description about the predefined operation templates is only exemplary, and is not intended to limit the scope of the present disclosure in any way. Those skilled in the art can understand that the predetermined operation template can be implemented in any suitable form.

FIG. 4B shows a schematic diagram 450 of a data analysis process for a two-way dialogue based on the heuristic information in FIG. 4A according to an embodiment of the present disclosure. In the embodiment shown in FIG. 4B , the user 101 inputs supplementary information according to the heuristic information provided by the data analysis device 105 , such as inputting "OK" or clicking a button with "OK". After receiving the supplementary information, the data analysis device 105 uses a predefined operation template or an operation determined in the operation model again according to the supplementary information input by the user to obtain the corresponding data analysis result.

Still referring to the example of FIG. 2, the result includes the text "If this outlier is broken down by activity, the number of "fishing" attacks was the first among all activities in 1960" 451, a chart 452, and further enlightening information 453 , which is "Fishing has 2 main aspects, which one do you need to know about?" and the three buttons "Male", "Non-Lethal", and "No Thanks". The user 101 can continue to provide supplementary information based on the further enlightening information 453 , such as selecting one of the three buttons "Male", "Non-fatal" and "No, thank you", so as to obtain corresponding data analysis results.

By using this two-way dialogue, the data analysis device 105 can expand the data analysis results by providing enlightening information to the user 101, thereby providing data analysis results that are more likely to meet the user's further needs from multiple angles or directions. This approach effectively improves the possibility for users to obtain the desired further data analysis results, and significantly improves user experience.

Several exemplary embodiments of the data analysis method and apparatus in a two-way conversational manner are described in more detail below. FIG. 5 shows a flowchart of a method 500 for data analysis according to an embodiment of the present disclosure. It should be understood that the method 500 may be executed by the processing unit 110 described with reference to FIG. 1 .

At 510, a data analysis request for a data set is received from a user in a dialog. Taking the embodiment of FIG. 1 as an example, a user 101 provides a data analysis request 102 to a data analysis device 105 , such as an input device 150 of the data analysis device 105 . For example, the user 101 may input the data analysis request 101 in the dialog box in the form of text, voice or a combination thereof, or may input the data analysis request 101 by clicking or touching a button, a drop-down box, a graph, a curve, or a text , or the data analysis request 101 can be input by dragging and dropping predetermined controls, graphics, text, and the like. It should be understood that the above examples for inputting the data analysis request 101 are for discussion purposes only, are not limiting, and are not intended to limit the scope of the present disclosure in any way.

In some embodiments, when the data analysis device 105 receives a data analysis request 101 from a user in text, voice or a combination thereof, the data analysis device 105 may save it in memory or a predetermined storage space for subsequent use. When detecting that the user 101 clicks or touches a button, a drop-down box, a graph, a curve, or a text, the data analysis device 105 can determine one or more events associated with the click or touch, and obtain and receive an event based on the event. Information about incoming data analysis requests. When it is detected that the user 101 drags a predetermined control, graphic, text, etc., the data analysis device 105 can determine one or more events associated with the drag, and obtain a data analysis request related to the received data based on the event. Related information.

At 520, based on the data analysis request, heuristic information is determined. In the embodiments of the present disclosure, the heuristic information is information different from the result generated for the user's data analysis request and used to guide the session between the user and the data analysis device so that it will not be interrupted or an error will be reported. For example, enlightening information can guide users to clarify certain concepts in their input data analysis requests, or provide users with other extended information related to data analysis results, and so on.

According to an embodiment of the present disclosure, the data analysis device 105 may determine the heuristic information in a variety of ways. In some embodiments, the data analysis device 105 may extract content items from the data analysis request, for example, words or phrases about places, times, dates, events, brands, categories, and the like. In some alternative embodiments, the data analysis device 105 may also determine, based on the extracted content items, the content items that are highly relevant thereto. Subsequently, the data analysis device 105 may determine whether at least one operation to be applied to the data set can be determined based on the extracted content item and/or the determined content item.

For example, the data analysis device 105 may perform linguistic analysis on the data analysis request, thereby determining the part of speech of the word in the data analysis request, such as "noun", "pronoun", "adverb", etc., and determining the definition of the word. role, such as "adverbial", "attribute", "predicate", etc., and/or determine other linguistic properties of the word. It should be understood that the above-mentioned linguistic analysis process can be realized by using a traditional linguistic analysis algorithm (such as a Part-Of-Speech (POS) tagging algorithm), which will not be repeated here.

Optionally, the data analysis device 105 may also detect the context of the data analysis request. During this process, the data analysis device 105 can determine the environment under which the data analysis request is made, the data analysis request by querying the content entered by the user within a predetermined period of time or within a predetermined number of sentences before inputting the data analysis request. What content item is the pronoun in the request referring to, what was omitted from the request, and so on.

Then, the data analysis device 105 may try to determine the at least one operation based on the obtained content item, linguistic analysis result, context and predefined data model. A predefined data model may include a content item and one or more operations associated with the content item. In one embodiment, each operation of a content item may, for example, be associated with a different linguistic mode. In this case, the data analysis device 105 can determine the linguistic mode of the content item according to the above linguistic analysis result and the context, so as to further determine the operation of the content item with the linguistic mode.

In some embodiments, if no operation can be determined, then the data analysis device 105 may consider that the identified content item has an incomprehensible meaning and needs to be clarified by the user. In this case, the data analysis device 105 may generate questions for the data analysis request based on the identified content item to prompt the user to provide clarifying information about the content item.

Alternatively, in other embodiments, if the data analysis device 105 is able to determine one or more operations based on the identified content item, the data analysis device 105 may determine a code segment for implementing the at least one operation, And determine the above heuristic information based on this code snippet. According to an embodiment of the present disclosure, a code segment is, for example, a program or a piece of code for implementing an operation associated with a content item. A content item may, for example, be an input or a part of an input of this code snippet, and may have a different class, purpose or use. A code fragment may include one or more operations performed in a certain order. The code segment may be a program generated on demand, dynamically and/or automatically; it may also be a pre-defined program stored in a specific memory. It should be understood that the code segments are flexibly configurable, and can be implemented in any suitable programming language or format, which is not intended to limit the scope of the present disclosure in any way.

In some embodiments, if the data analysis device 105 determines a plurality of code fragments based on the identified content item, the data analysis device 105 may sort the plurality of code fragments, for example, according to the linguistic analysis results for the data analysis request and/or contextual information to score these code snippets, and then sort the code snippets according to the score. A code snippet with a higher score means that the code snippet is more likely to meet the user's data analysis needs. The data analysis device 105 can provide the user 101 with a data analysis result obtained according to the code fragment with the highest score. In addition, the data analysis device 105 may provide the user 101 with options corresponding to code fragments with slightly lower scores or results obtained according to these code fragments as enlightening information. Such heuristic information includes extended information on the data analysis results, thereby improving the possibility of providing data analysis results that meet user requirements.

According to some alternative embodiments of the present disclosure, the data analysis device 105 may also determine heuristic information by expanding the data analysis request based on content items in the data analysis request, results for the data analysis request, predetermined expansion rules, and the like. In some embodiments, the data analysis device 105 may determine other operations associated with the result for the data analysis request, for example, the result may be extracted from the content item to find a matching operation according to a pre-established data model. Then, the data analysis device 105 can obtain a code segment based on the determined operation, and run the obtained code segment to obtain a result, so as to provide the result to the user 101 as enlightening information.

As an alternative, in some other embodiments, the data analysis device 105 may also apply the content items in the data analysis request, the content items extracted from the results of the data analysis request, etc. to predetermined extension rules, so as to obtain There are one or more extended content items associated with the content item. At this time, the data analysis device 105 may try to determine the operation associated with the extended content item, obtain the corresponding code fragment, and then obtain the extended analysis result by running the code fragment.

At 530, the heuristic information is provided to the user to enable the user to provide supplemental information associated with the data analysis request based on the heuristic information. In some embodiments, the data analysis device 105 may provide the extended analysis results obtained above as enlightening information to the user for selection by the user.

In some alternative embodiments, the data analysis device 105 may also only provide the user 101 with the identification of the code fragment associated with the extended content item as heuristic information, for example, displaying it to the user in the form of serial number, keyword, etc., only when the user 101 When a corresponding serial number or keyword is clicked or input, the data analysis device 105 runs the corresponding code segment to obtain the extended analysis result. In this way, unnecessary system resource consumption can be reduced, and operation efficiency and speed can be improved.

In some other alternative embodiments, at 530, the data analysis device 105 may generate questions for the data analysis request based on the identified content item as enlightening information to the user to prompt the user 101 to provide clarification on the content item sexual information.

According to an embodiment of the present disclosure, after receiving the enlightening information, the user 101 may provide supplementary information associated with the data analysis request. The supplementary information may be clarification information on the questions raised by the data analysis device 105 regarding the data analysis request, or may be selective information on whether to view the extended analysis results and which extended analysis results to view. After receiving the supplementary information from the user, the data analysis device 105 can determine the data analysis result associated with the supplementary information, and provide the determined data analysis result to the user. In this manner, the possibility of the user obtaining the required data analysis result can be effectively improved, and the user experience is significantly improved.

According to an embodiment of the present disclosure, the data analysis device 105 stores at least one item of the data analysis request and/or supplementary information as a user profile, so as to subsequently provide relevant data analysis results based on the user profile. The user profile may include the user's data analysis history information, which may accurately reflect the user's data analysis habits.

In some embodiments, even if the user does not submit any data analysis request, the data analysis device 105 can automatically mine the data in the data set according to the user profile, and actively provide enlightening information to the user. In some alternative or additional embodiments, the data analysis device 105 may also obtain profiles of other users, and determine a data analysis strategy based on the profiles of the user and/or the profiles of other users. For example, when most users want to obtain abnormal points of data in the past period of time, the data analysis strategy may be "analyze abnormal points", for example. It should be understood that this is exemplary only. In the embodiments of the present disclosure, the data analysis policy may also include the average result, extreme value or other information of the analyzed data, may also include the priority or execution order of these analyzes, and may also include any other appropriate analysis methods. Then, the data analysis device 105 can analyze the data according to the determined data analysis strategy, so as to obtain enlightening information and provide it to the user. Users can determine the data analysis results they want to view according to the heuristic information. In this way, users can better understand the data and effectively guide the data analysis dialogue.

An embodiment of the data analysis method in a two-way dialogue mode according to the present disclosure will now be described in more detail with reference to FIG. 6 . FIG. 6 shows a flowchart of a method 600 for data analysis according to an embodiment of the present disclosure. It should be understood that the method 600 may be executed by the processing unit 110 described with reference to FIG. 1 , and may be regarded as a specific implementation manner of the method 500 . It should also be understood that the method 600 is only exemplary and not restrictive, and various operations in the method 600 may be increased or decreased appropriately, and may also be performed in any other appropriate order.

At 610, the data analysis facility 105 receives a data analysis request for a data set from a user. Still referring to the embodiment shown in FIG. 3 , the data analysis request received by the data analysis device 105 from the user 101 is, for example, “Please list dangerous countries by year”, as shown in 310 . At 620, the data analysis device 105 extracts the content item from the data analysis request. Continuing to refer to the embodiment of FIG. 3 , the data analysis device 105 requests from the data analysis that the content items in "Please list dangerous countries by year" are, for example, "year", "dangerous" and "country".

At 630, the data analysis device 105 determines whether an operation to be applied to the data set can be determined based on the content item. In the above embodiment, since the two content items "year" and "country" have defined associated operations in the data model, but the content item "danger" has not defined the corresponding operation, the data analysis device 105 Could not determine the action associated with the content item "Dangerous".

At 640, questions for the data analysis request are generated based on the content item as enlightening information. For example, the data analysis device 105 may generate a question for the data analysis request 102, such as "Please explain what is meant by 'dangerous' in 'dangerous country'?". At 680, the data analysis device 105 provides the heuristic information to the user, that is, presents the above-mentioned question to the user, as shown in 320 of FIG. 3 .

At 690, supplemental information is received from the user. In the embodiment shown in FIG. 3 , the user 101 inputs the following clarification information: "the number of fatal attacks is higher than 100", as shown in 330, to explain the meaning of the content item "dangerous". Method 600 then proceeds to 620 where data analysis device 105 extracts content items from the user's supplemental information. For example, the data analysis device 105 may extract the content items "fatal" and "number of attacks" from the supplementary information "the number of fatal attacks is higher than 100".

Then, at 630, the data analysis device 105 determines whether an operation to be applied to the data set can be determined based on the extracted content item. In this embodiment, it is assumed that both "fatal" and "number of attacks" belong to the content items in the established data model, so the data analysis device 105 can determine the corresponding 200 operations. Then, at 650, the data analysis device 105 determines a code segment for implementing the determined operation. At 660 , the data analysis device 105 can generate a corresponding data analysis result by executing the code segment, and provide the result to the user 101 .

It should be understood that the above examples are illustrative only and not restrictive. In some other embodiments according to the present disclosure, if the data analysis device 105 judges at 630 that the operation to be applied to the data set still cannot be obtained according to the content items (for example, "fatal" and "number of attacks") determined by the supplementary information , then the data analysis device 105 can continue to provide enlightening information to the user 101, so that the user 101 can provide further clarification information.

In other embodiments according to the present disclosure, if the data analysis request received by the data analysis device 105 at 610 is as shown at 420 in FIG. The content item "Year" was identified in . Since operations associated with "year" are stored in the data model, the data analysis device 105 determines at 630 that operations to be applied to the data set can be determined based on the content item.

Then, at 650, the data analysis device 105 determines a code segment for implementing the above operations. At 660 , the data analysis device 105 can generate a corresponding data analysis result by executing the code segment, and provide the result to the user 101 , as shown at 430 .

In some embodiments, the data analysis device 105 may also determine heuristic information based on data analysis results. As shown in the embodiment of FIG. 6 , after the data analysis device 105 provides the data analysis result (that is, the curve of the number of attacks by year) to the user 101 at 660, it may also determine the extended analysis result at 670 based on the data analysis result, And at 680, the extended analysis result is provided to the user 101 as enlightening information. The heuristic information, such as "Do you want to know more about the outlier in 1960?", is shown as 440 in FIG. 4 , and corresponding candidate items 441 and 442 .

At 690, the data analysis device 105 receives supplemental information from the user, such as "OK" indicated by 443 in FIG. 4B. In some embodiments, through contextual analysis, the data analysis device 105 may determine the supplementary information input by the user as a "question to know more about outliers in 1960". Then at 620, the data analysis device 105 extracts content items such as "1960" and "outlier value" etc. from the supplementary information.

Then, at 630, the data analysis device 105 determines whether an operation to be applied to the data set can be determined based on the extracted content item. In this embodiment, since both "1960" and "abnormal value" belong to the content items in the established data model, the data analysis device 105 can determine the corresponding 200 operations. Then, at 650, the data analysis device 105 determines a code segment for implementing the determined operation. At 660 , the data analysis device 105 executes the code segment to generate a corresponding data analysis result, and provides the result to the user 101 , as shown in 451 and 452 .

It should be understood that the above examples are illustrative only and not restrictive. In other embodiments according to the present disclosure, after providing the above-mentioned data analysis results, the data analysis device 105 can also continue to provide enlightening information to the user 101, such as 453 in FIG. 4B, so that the user can view more relevant data analysis result.

According to an embodiment of the present disclosure, the user interface between the user 101 and the data analysis device 105 may include one or more dialogs. In some embodiments, the dialog described above in conjunction with the embodiments of FIGS. 5-6 can be considered as the first dialog in the user interface. When the data analysis device 105 receives another data analysis request from the user 101, it can create a second dialog different from the first dialog in a drag-and-drop manner, and can provide the user with an analysis method for the other data in the second dialog. The requested data analysis results. FIG. 7 illustrates a user interface 700 for multiple dialogs according to an embodiment of the disclosure. In the embodiment shown in FIG. 7, during the first dialogue 710, the user 101 creates the second dialogue 720 by clicking or dragging the text or the button "gender" (shown by 701) on the left side of the user interface . In this second dialog, the data analysis device 105 may provide the result of the data analysis request 721 for "gender", as shown at 722 . In this way, users can perform multiple data analysis tasks in multiple conversations at the same time, which effectively improves work efficiency and is convenient for users.

According to a further embodiment of the present disclosure, options may be provided to the user in each dialog to present only the parts related to the data analysis results. FIG. 8 illustrates a user interface 800 according to an embodiment of the disclosure. In FIG. 8, the user makes only the portions 810, 820, and 830 relevant to the data analysis results visible by clicking on relevant buttons or controls on the user interface. The user can arrange the view and zoom in and out the size by dragging these parts 810 , 820 and 830 . At this time, sections related to data analysis requests, heuristic information, etc. are not visible. In this way, users can easily obtain the required data analysis results, such as directly generating reports or charts. In this way, the use of the user is facilitated to a certain extent, and the user experience is improved.

According to an embodiment of the present disclosure, the data analysis device 105 can determine the user's preference or interest by learning the data analysis request of the user 101, thereby establishing a user profile. The data analysis device 105 can also update and improve the user profile in the dialogue with the user 101, so as to better understand and analyze the user's needs and intentions. For example, regarding the data set 200 of shark attack records, if the user 101 is preparing to write a text about the analysis of shark attacks in Australia, the user probably does not need data analysis about the United States, but only needs data analysis about Australia. In this case, the data analysis device 105 may consider that the program segment composed of various operations related to the content item in Australia has a higher score. In this way, the data analysis result provided to the user by the data analysis device 105 is likely to be related to Australia, so that the user's needs can be better met.

The methods and functions described herein may be performed at least in part by one or more hardware logic components. Illustrative types of hardware logic components that may be used include, for example and without limitation, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), System on Chips (SOCs), Complex Programmable Logic Devices (CPLD) and so on.

Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

In addition, while operations are depicted in a particular order, this should be understood to require that such operations be performed in the particular order shown, or in sequential order, or that all illustrated operations should be performed to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while the above discussion contains several specific implementation details, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate implementations can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.

Some example implementations of the present disclosure are listed below.

Embodiments of the present disclosure include a computer-implemented method. The method includes: receiving a data analysis request for a data set from a user in a dialog; based on the data analysis request, determining heuristic information for guiding the dialog that is different from a result of the data analysis request; and providing the heuristic information to the user to enable the user to provide supplemental information associated with the data analysis request based on the heuristic information.

In some embodiments, determining heuristic information includes: extracting content items from the data analysis request; determining whether at least one operation to be applied to the data set can be determined based on the identified content items; The content item determines the at least one action, and a question for the data analysis request is generated based on the identified content item, the question to elicit the user to provide clarifying information about the content item.

In some embodiments, determining whether at least one operation to be applied to the data set can be determined based on the identified content item comprises: performing a linguistic analysis on the data analysis request; detecting a context of the data analysis request; and An attempt is made to determine said at least one operation based on said content item, said linguistic analysis result, said context and a predefined data model.

In some embodiments, the method may further include: in response to being able to determine the at least one operation based on the identified content item, determining a code snippet for implementing the at least one operation; and determining the Inspiring information.

In some embodiments, determining the heuristic information includes generating the heuristic information by extending the data analysis request based on at least one of: content items in the data analysis request, results, along with predetermined expansion rules.

In some embodiments, the method may further include: in response to receiving the supplemental information from the user, determining a data analysis result associated with the supplemental information; and providing the determined data analysis to the user. result.

In some embodiments, the dialog is the first dialog in the user interface, and the method may further include: in response to receiving a further data analysis request from the user, creating a dialog different from the first dialog in a dragging manner a second session of the first session; and providing the user with data analysis results for the further data analysis request in the second session.

In some embodiments, the method may further include: storing at least one of the data analysis request and the supplementary information as a user profile, so as to provide relevant data analysis results based on the user profile.

Embodiments of the present disclosure include an electronic device including: a processing unit; a memory coupled to the processing unit and storing instructions that, when executed by the processing unit, perform the following actions: receive a message from a user in a dialog a data analysis request for a data set; based on the data analysis request, determine heuristic information for guiding the conversation that differs from the results for the data analysis request; and provide the user with the heuristic information to enable the user to provide supplemental information associated with the data analysis request based on the heuristic information.

In some embodiments, determining heuristic information may include: extracting content items from the data analysis request; determining whether at least one operation to be applied to the data set can be determined based on the identified content items; The at least one action is determined based on the content item, and a question for the data analysis request is generated based on the identified content item, the question to elicit the user to provide clarifying information about the content item.

In some embodiments, determining whether at least one operation to be applied to the data set can be determined based on the identified content item may comprise: performing a linguistic analysis on the data analysis request; detecting a context of the data analysis request; and attempting to determine said at least one operation based on said content item, said linguistic analysis result, said context and a predefined data model.

In some embodiments, the actions may further include: in response to being able to determine the at least one operation based on the identified content item, determining a code snippet for implementing the at least one operation; and determining the at least one operation based on the code snippet Inspiring information.

In some embodiments, determining the heuristic information may include: generating the heuristic information by extending the data analysis request based on at least one of: a content item in the data analysis request, for the data analysis request , and the predetermined expansion rules.

In some embodiments, the actions may further include: in response to receiving the supplemental information from the user, determining data analysis results associated with the supplemental information; and providing the determined data to the user Analyze the results.

In some embodiments, the dialog is the first dialog in the user interface, and the action may further include: in response to receiving a further data analysis request from the user, creating a dialog different from the a second session of the first session; and providing the user with data analysis results for the further data analysis request in the second session.

In some embodiments, the actions may further include: storing at least one of the data analysis request and the supplementary information as a user profile, so as to provide relevant data analysis results based on the user profile.

Embodiments of the present disclosure also provide a computer program product stored in a non-transitory computer storage medium and comprising machine-executable instructions that, when executed in a device, cause the An apparatus for: receiving a data analysis request for a data set from a user in a dialog; determining, based on the data analysis request, heuristic information for guiding the dialog that differs from a result for the data analysis request; The user provides the heuristic information to enable the user to provide supplemental information associated with the data analysis request based on the heuristic information.

In some embodiments, the machine-executable instructions, when executed in the device, further cause the device to: extract content items from the data analysis request; set at least one operation; and in response to the at least one operation being unable to be determined based on the content item, generating a question for the data analysis request based on the identified content item, the question being used to elicit the user to provide information about the Clarifying information for the above content item.

In some embodiments, the machine-executable instructions, when executed in the device, further cause the device to: perform linguistic analysis on the data analysis request; detect the context of the data analysis request; Attempt to determine the at least one operation based on the linguistic analysis result, the context and the predefined data model.

In some embodiments, the machine-executable instructions, when executed in the device, further cause the device to: in response to being able to determine the at least one operation based on the identified content item, determine code for implementing the at least one operation a fragment; and determining the heuristic information based on the code fragment.

In some embodiments, the machine-executable instructions, when executed in the device, further cause the device to: generate the heuristic information by extending the data analysis request based on at least one of: The content item, the result of the analysis request for the data, and the predetermined expansion rule.

In some embodiments, the machine-executable instructions, when executed in a device, further cause the device to: in response to receiving the supplemental information from the user, determine a data analysis result associated with the supplemental information; and providing the determined data analysis result to the user.

In some embodiments, the dialog is a first dialog in a user interface, and the machine-executable instructions, when executed in the device, further cause the device to: respond to receiving a further data analysis request from the user , establishing a second dialog different from the first dialog in a drag-and-drop manner; and providing the user with a data analysis result for the further data analysis request in the second dialog.

In some embodiments, the machine-executable instructions, when executed in a device, further cause the device to: store at least one of the data analysis request and the supplemental information as a user profile for use based on the User profiles provide relevant data analysis results.

Although the disclosure has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims (20)

1. A computer-implemented method, comprising:

receiving a data analysis request for a data set from a user in a dialog;

extracting a content item from the data analysis request;

comparing the extracted content items to a data model for the data set, the data model including a plurality of content items defined in the data model and one or more operations associated with each of the plurality of content items to be applied to the data set, the one or more operations based on at least one of: historical statistics, a profile or preference of the user, or a record of access by a plurality of users;

based on the comparison, determining that the extracted content item and associated operations to be applied to the data set are undefined in the data model;

in response to the determination, generating heuristic information for directing the dialog to prompt the user to provide clarification information associated with the extracted content item and different from a result of the request for data analysis; and

providing the heuristic information to the user to enable the user to provide supplemental information associated with the data analysis request based on the heuristic information.

2. The method of claim 1, wherein generating the heuristic information for directing the dialog to prompt the user to provide the clarity information associated with the extracted content item comprises:

generating a question for the data analysis request based on the extracted content item.

3. The method of claim 1, further comprising:

performing linguistic analysis on the data analysis request;

detecting a context of the data analysis request; and

generating the heuristic information in response to determining that the associated operation to be applied to the dataset cannot be determined based on the linguistic analysis results, the context, and the associated operation that is not defined in the data model.

4. The method of claim 1, further comprising:

extracting at least one additional content item from the data analysis request;

determining that the at least one additional content item is one of the plurality of content items and has at least one associated operation defined in the data model;

determining a code segment for implementing the at least one associated operation defined in the data model; and

determining the heuristic information based on the code snippet.

5. The method of claim 1, wherein the heuristic information is generated based on at least one of:

the extracted content item in the data analysis request, an

Predefined rules for extending the data analysis request.

6. The method of claim 1, further comprising:

receiving the supplemental information from the user;

in response to receiving the supplemental information from the user, determining a data analysis result associated with the supplemental information; and

providing the determined data analysis results to the user.

7. The method of claim 6, wherein the determined data analysis results are provided to the user as one of:

a graph;

a table;

a text;

audio frequency; and

and (6) video.

8. The method of claim 6, the supplemental information received from the user including at least one content item from the plurality of content items in the data model, and determining the data analysis results associated with the supplemental information includes applying corresponding one or more operations defined for the at least one content item in the data model to the data set.

9. The method of claim 1, further comprising:

receiving the supplemental information from the user; and

storing at least one of the data analysis request and the supplemental information as a user profile to provide relevant data analysis results based on the user profile.

10. The method of claim 1, wherein generating the heuristic information for directing the dialog to prompt the user to provide the clarity information associated with the extracted content item further comprises:

providing a list of options selectable by the user.

11. The method of claim 1, wherein the data set includes a table having a plurality of rows representing data records and a plurality of columns representing data dimensions of the data records, and the plurality of content items in the data model includes at least the data dimensions of the data records.

12. A computing device, comprising:

a processing unit; and

a memory coupled to the processing unit and storing instructions that, when executed by the processing unit, cause the computing device to perform a set of operations comprising:

receiving a data analysis request for a data set from a user in a dialog;

extracting a content item from the data analysis request;

comparing the extracted content items to a data model for the data set

In one embodiment, the data model includes a plurality of content items defined in the data model and one or more operations associated with each of the plurality of content items to be applied to the data set, the one or more operations based on at least one of: historical statistics, the user's profile or preferences, or access records of multiple users

Based on the comparison, determining that the extracted content item and associated operation to be applied to the data set are undefined in the data model;

in response to the determination, generating a dialog for directing the dialog to prompt the user to provide clarification information associated with the extracted content item and different than for the extracted content item

Heuristic information of the result of the data analysis request; and

providing the heuristic information to the user to enable the user to be based on the heuristic information

Heuristic information provides supplemental information associated with the data analysis request.

13. The computing device of claim 12, wherein generating the heuristic information for directing the dialog to prompt the user to provide the clarity information associated with the extracted content item comprises:

generating a question for the data analysis request based on the content item.

14. The computing device of claim 12, wherein the heuristic information is generated based on at least one of:

the extracted content item in the data analysis request, an

Predefined rules for extending the data analysis request.

15. The computing device of claim 12, the set of operations further comprising:

receiving the supplemental information from the user;

in response to receiving the supplemental information from the user, determining a data analysis result associated with the supplemental information; and

providing the determined data analysis results to the user.

16. The computing device of claim 12, wherein the conversation is a first conversation in a user interface, and the set of operations further comprises:

in response to receiving a second data analysis request from the user, establishing a second conversation different from the first conversation in a drag-and-drop manner; and

providing data analysis results for the second data analysis request to the user in the second dialog.

17. The computing device of claim 12, the set of operations further comprising:

receiving the supplemental information from the user; and

storing at least one of the data analysis request and the supplemental information as a user profile to provide relevant data analysis results based on the user profile.

18. The computing device of claim 12, further comprising:

performing linguistic analysis on the data analysis request;

detecting a context of the data analysis request; and

generating the heuristic information in response to determining that the associated operation to be applied to the dataset cannot be determined based on the linguistic analysis results, the context, and the associated operation that is not defined in the data model.

19. The computing device of claim 12, the set of operations further comprising:

extracting at least one additional content item from the data analysis request;

determining that the at least one additional content item is one of the plurality of content items and has at least one associated operation defined in the data model;

determining a code segment for implementing the at least one associated operation defined in the data model; and

determining the heuristic information based on the code snippet.

20. A non-transitory machine-readable medium storing machine-executable instructions that, when executed in a device, cause the device to:

receiving a data analysis request for a data set from a user in a dialog;

extracting a content item from the data analysis request;

comparing the extracted content items to a data model for the data set, the data model including a plurality of content items defined in the data model and one or more operations associated with each of the plurality of content items to be applied to the data set, the one or more operations based on at least one of: historical statistics, a user's profile or preferences, or access records for multiple users;

based on the comparison, determining that the extracted content item and associated operations to be applied to the data set are undefined in the data model;

in response to the determination, generating heuristic information for directing the dialog to prompt the user to provide clarity information associated with the extracted content item and different from a result of the request for data analysis; and

providing the heuristic information to the user to enable the user to provide supplemental information associated with the data analysis request based on the heuristic information.

Images